Comparison of telephone recordings and professional microphone recordings for early detection of Parkinson's disease, using mel-frequency cepstral coefficients with Gaussian mixture models

Laetitia Jeancolas; Graziella Mangone; Jean Christophe Corvol; Marie Vidailhet; Stéphane Lehericy; Badr Eddine Benkelfat; Habib Benali; Dijana Petrovska-Delacretaz

doi:10.21437/Interspeech.2019-2825

Comparison of telephone recordings and professional microphone recordings for early detection of Parkinson's disease, using mel-frequency cepstral coefficients with Gaussian mixture models

Laetitia Jeancolas
, Graziella Mangone
, Jean Christophe Corvol
, Marie Vidailhet
, Stéphane Lehericy
, Badr Eddine Benkelfat
, Habib Benali
, Dijana Petrovska-Delacretaz

Institut Polytechnique de Paris
Sorbonne Université
Département de Neurologie
AP-HP
Institut du Cerveau et de la Moelle épinière (ICM)
PERFORM Centre
Concordia University

Research output: Contribution to journal › Conference article › peer-review

16 Citations (Scopus)

Abstract

Vocal impairments are among the earliest symptoms in Parkinson's Disease (PD). We adapted a method classically used in speech and speaker recognition, based on Mel-Frequency Cepstral Coefficients (MFCC) extraction and Gaussian Mixture Model (GMM) to detect recently diagnosed and pharmacologically treated PD patients. We classified early PD subjects from controls with an accuracy of 83%, using recordings obtained with a professional microphone. More interestingly, we were able to classify PD from controls with an accuracy of 75 % based on telephone recordings. As far as we know, this is the first time that audio recordings from telephone network have been used for early PD detection. This is a promising result for a potential future telediagnosis of Parkinson's disease.

Original language	English
Pages (from-to)	3033-3037
Number of pages	5
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	2019-September
DOIs	https://doi.org/10.21437/Interspeech.2019-2825
Publication status	Published - 1 Jan 2019
Event	20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, INTERSPEECH 2019 - Graz, Austria Duration: 15 Sept 2019 → 19 Sept 2019

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Acoustic analysis
Parkinson's disease
Speech disorder
Telediagnosis
Telephone recordings

Access to Document

10.21437/Interspeech.2019-2825

Cite this

Jeancolas, L., Mangone, G., Corvol, J. C., Vidailhet, M., Lehericy, S., Benkelfat, B. E., Benali, H., & Petrovska-Delacretaz, D. (2019). Comparison of telephone recordings and professional microphone recordings for early detection of Parkinson's disease, using mel-frequency cepstral coefficients with Gaussian mixture models. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2019-September, 3033-3037. https://doi.org/10.21437/Interspeech.2019-2825

Jeancolas, Laetitia ; Mangone, Graziella ; Corvol, Jean Christophe et al. / Comparison of telephone recordings and professional microphone recordings for early detection of Parkinson's disease, using mel-frequency cepstral coefficients with Gaussian mixture models. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2019 ; Vol. 2019-September. pp. 3033-3037.

@article{b9a1c7d5c9b74b1dbe929f807bb1a759,

title = "Comparison of telephone recordings and professional microphone recordings for early detection of Parkinson's disease, using mel-frequency cepstral coefficients with Gaussian mixture models",

abstract = "Vocal impairments are among the earliest symptoms in Parkinson's Disease (PD). We adapted a method classically used in speech and speaker recognition, based on Mel-Frequency Cepstral Coefficients (MFCC) extraction and Gaussian Mixture Model (GMM) to detect recently diagnosed and pharmacologically treated PD patients. We classified early PD subjects from controls with an accuracy of 83\%, using recordings obtained with a professional microphone. More interestingly, we were able to classify PD from controls with an accuracy of 75 \% based on telephone recordings. As far as we know, this is the first time that audio recordings from telephone network have been used for early PD detection. This is a promising result for a potential future telediagnosis of Parkinson's disease.",

keywords = "Acoustic analysis, Parkinson's disease, Speech disorder, Telediagnosis, Telephone recordings",

author = "Laetitia Jeancolas and Graziella Mangone and Corvol, \{Jean Christophe\} and Marie Vidailhet and St{\'e}phane Lehericy and Benkelfat, \{Badr Eddine\} and Habib Benali and Dijana Petrovska-Delacretaz",

note = "Publisher Copyright: Copyright {\textcopyright} 2019 ISCA; 20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, INTERSPEECH 2019 ; Conference date: 15-09-2019 Through 19-09-2019",

year = "2019",

month = jan,

day = "1",

doi = "10.21437/Interspeech.2019-2825",

language = "English",

volume = "2019-September",

pages = "3033--3037",

journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

issn = "2308-457X",

publisher = "International Speech Communication Association",

}

Jeancolas, L, Mangone, G, Corvol, JC, Vidailhet, M, Lehericy, S, Benkelfat, BE, Benali, H & Petrovska-Delacretaz, D 2019, 'Comparison of telephone recordings and professional microphone recordings for early detection of Parkinson's disease, using mel-frequency cepstral coefficients with Gaussian mixture models', Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2019-September, pp. 3033-3037. https://doi.org/10.21437/Interspeech.2019-2825

Comparison of telephone recordings and professional microphone recordings for early detection of Parkinson's disease, using mel-frequency cepstral coefficients with Gaussian mixture models. / Jeancolas, Laetitia; Mangone, Graziella; Corvol, Jean Christophe et al.
In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2019-September, 01.01.2019, p. 3033-3037.

Research output: Contribution to journal › Conference article › peer-review

TY - JOUR

T1 - Comparison of telephone recordings and professional microphone recordings for early detection of Parkinson's disease, using mel-frequency cepstral coefficients with Gaussian mixture models

AU - Jeancolas, Laetitia

AU - Mangone, Graziella

AU - Corvol, Jean Christophe

AU - Vidailhet, Marie

AU - Lehericy, Stéphane

AU - Benkelfat, Badr Eddine

AU - Benali, Habib

AU - Petrovska-Delacretaz, Dijana

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Vocal impairments are among the earliest symptoms in Parkinson's Disease (PD). We adapted a method classically used in speech and speaker recognition, based on Mel-Frequency Cepstral Coefficients (MFCC) extraction and Gaussian Mixture Model (GMM) to detect recently diagnosed and pharmacologically treated PD patients. We classified early PD subjects from controls with an accuracy of 83%, using recordings obtained with a professional microphone. More interestingly, we were able to classify PD from controls with an accuracy of 75 % based on telephone recordings. As far as we know, this is the first time that audio recordings from telephone network have been used for early PD detection. This is a promising result for a potential future telediagnosis of Parkinson's disease.

AB - Vocal impairments are among the earliest symptoms in Parkinson's Disease (PD). We adapted a method classically used in speech and speaker recognition, based on Mel-Frequency Cepstral Coefficients (MFCC) extraction and Gaussian Mixture Model (GMM) to detect recently diagnosed and pharmacologically treated PD patients. We classified early PD subjects from controls with an accuracy of 83%, using recordings obtained with a professional microphone. More interestingly, we were able to classify PD from controls with an accuracy of 75 % based on telephone recordings. As far as we know, this is the first time that audio recordings from telephone network have been used for early PD detection. This is a promising result for a potential future telediagnosis of Parkinson's disease.

KW - Acoustic analysis

KW - Parkinson's disease

KW - Speech disorder

KW - Telediagnosis

KW - Telephone recordings

U2 - 10.21437/Interspeech.2019-2825

DO - 10.21437/Interspeech.2019-2825

M3 - Conference article

AN - SCOPUS:85074694606

SN - 2308-457X

VL - 2019-September

SP - 3033

EP - 3037

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

T2 - 20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, INTERSPEECH 2019

Y2 - 15 September 2019 through 19 September 2019

ER -

Jeancolas L, Mangone G, Corvol JC, Vidailhet M, Lehericy S, Benkelfat BE et al. Comparison of telephone recordings and professional microphone recordings for early detection of Parkinson's disease, using mel-frequency cepstral coefficients with Gaussian mixture models. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2019 Jan 1;2019-September:3033-3037. doi: 10.21437/Interspeech.2019-2825

Comparison of telephone recordings and professional microphone recordings for early detection of Parkinson's disease, using mel-frequency cepstral coefficients with Gaussian mixture models

Abstract

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this